Analyze web data based on TF-IDF, Cosine Similarity
This web application could run on the Ubuntu 20.04 LTS (WSL2) and is compatible with only Python 3.
Elasticsearch is used to store crawled data. Therefore, you need to run Elasticsearch before you run the web application.
Python requirements are as below:
validators
requests
flask
numpy
nltk
bs4
NLTK requirements are as below:
$ python -m nltk.downloader punkt
$ python -m nltk.downloader stopwords
$ python ./app.py